Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

gemma4:e2b-mlx

OLLAMA GGUF
Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
84 vs 82
Hardware Fit
66 vs 99
Quality Score
92 vs 75

Hardware

qwen3.8:27b gemma4:e2b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen3.8:27b gemma4:e2b-mlx
Tokens/sec29.470.4
First chunk306 ms96 ms
TTFT4.8 s96 ms
Load time5.3 s2.5 s
Memory usage16.2 GB5.7 GB
Memory %13%36%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

gemma4:e2b-mlx

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:e2b-mlx

Reasoning
14/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.8:27b details | View gemma4:e2b-mlx details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest